Madar Bandu, B. Madhava Rao and Vijay Kumar Lakshetty |
Computer Science and Engineering, Anurag University, Hyderabad, Telangana, India.
Abstract
Many economies rely heavily on agriculture, and in order to guarantee food security and sustainable farming methods, precise crop forecasting has become more and more crucial. Uncertainty in weather, soil fertility, and pest infestations frequently limits the use of traditional crop yield prediction techniques. With the development of contemporary technologies, machine learning provides strong instruments for evaluating intricate and sizable agricultural datasets in order to make accurate predictions. Taking into account important variables like soil type, rainfall, temperature, humidity, and past yield data, this study focuses on crop prediction using machine learning techniques. To categorize and suggest the best crops for a particular area, algorithms like Decision Trees, Random Forest, Support Vector Machines, and Neural Networks are used. The suggested system helps farmers minimize crop failure risk, maximize resource use, and make data-driven decisions.
Keywords: Crop prediction, Crop recommendation, Decision tree, Machine learning, Rainfall prediction, SVM.
View PDF